RBF NEURAL NETWORK-BASED METHOD FOR SEA SURFACE WIND SPEED INVERSION FROM MARINE RADAR IMAGE

摘要

An RBF neural network-based method for sea surface wind speed inversion from a marine radar image, comprising four parts: marine radar image data preprocessing, RBF neural network input layer construction, RBF neural network model determination, and sea surface wind speed information extraction. The sea surface wind speed inversion process is completed on the basis of a model obtained by training a single hidden layer RBF neural network; a sample of the RBF neural network input layer is constructed by using a normalized result of a sea surface wind field energy spectrum, sensor information, and sea condition information; meanwhile, applying a subtractive clustering algorithm is proposed so as to determine the number of hidden layer units determined by the neural network and a center and extension constant of a basis function according to a density indicator of an input sample and a clustering determining condition, and a network output layer connection weight value is obtained by using recursive least squares.